Protocol
Detect stagnation separately from completion
More motion is not the same thing as more progress.
When it fits
- An agent is still acting but the task state is not improving.
When to avoid it
- Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count.
Why it matters
Track a small progress signal—remaining checklist items, failing tests, unresolved claims, changed artifacts or another task-specific state. If several iterations repeat without reducing the remaining work, stop the normal loop and trigger replanning or human review. Do not let lack of progress masquerade as persistence.
Steps
- The loop can identify 'not done and not improving' as a state distinct from both success and ordinary progress.
An example
If three coding iterations leave the same two tests failing with nearly identical edits, switch from retrying to diagnosis.
Check your result
The loop can identify 'not done and not improving' as a state distinct from both success and ordinary progress.
Keep this limit in mind
- Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count.
Evidence and sources
Long-horizon agent failure syntheses report compounding planning/execution failures and stalled behavior, supporting explicit progress diagnostics rather than outcome-only monitoring.
Some valid work has delayed visible progress; choose signals that fit the task rather than using one generic iteration count.
Beyond the Leaderboard: A Synthesis of Tool-Use, Planning, and Reasoning Failures in Large Language Model Agents · See source record